© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106227
    Prev
    Next
    INDEX
    Explanations

    system

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the word “system.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     assesses
    -1.21
    素直
    -1.12
    仕方ない
    -1.11
    変な
    -1.11
    も含
    -1.09
    癒し
    -1.09
     volledig
    -1.08
    かわい
    -1.07
     ."
    -1.05
     oversees
    -1.05
    POSITIVE LOGITS
     system
    2.56
     SYSTEM
    2.17
     systems
    2.17
     System
    2.16
    system
    2.13
    SYSTEM
    2.00
    ystem
    1.98
     система
    1.95
    getSystem
    1.94
     系统
    1.90
    Activations Density 0.102%

    No Known Activations